Epileptiform activities can be detected by scanning the electroencephalogram (EEG) signals of an epileptic patient. Since EEG provides multi-channel signals, it is an opportunity to employ multi-spectrum signal processing techniques for improving the accuracy of signal separation or feature extraction. Although multi-channel signals provide stronger characteristics than a single signal for feature extraction, taking all of the EEG signals into consideration may interfere with the accuracy of epileptiform discharge detection because a part of the signals that do not contain the epileptic activity will be treated as noise. In this paper, we developed a new signature analysis scheme, grouped-channel restricted band analysis (GRBA), for interictal epileptiform discharges (IED) detection from EEG signals. Unlike most traditional epileptic activity detection techniques that inaccurately take single or all EEG signals into consideration, GRBA simultaneously considers three important characteristics of epileptiform discharge waves, i.e. multispectral, finite spread, and specific duration, to detect epileptiform discharges efficiently. A series of experiments were conducted to compare GRBA with traditional feature-classifier methods and the non-grouped approach to evaluate this novel approach by the correct detection rate (Rc) and receiver operating characteristic (ROC) curves. The experimental results showed that our new signature analysis scheme, GRBA, had a superior quality. Moreover, we observed that the area under ROC curves and the Rc for GRBA were as high as 0.9479 and 94.1%, respectively.
|Journal||Biomedical Engineering - Applications, Basis and Communications|
|Publication status||Published - 2015 Apr 25|
All Science Journal Classification (ASJC) codes
- Biomedical Engineering